_1778514715081.png?width=400&height=300&quality=80&resize=cover)
Vertical to Horizontal Video Reframe
ashree
627
Image to Image
Lora Trainer
Qwen
Train a custom Qwen Image Edit 2511 LoRA from a folder of images. Florence 2 auto-captions, Musubi trains, and a built-in test section previews results.
Qwen LoRA Trainer with Auto-Caption
Train a custom Qwen Image Edit 2511 LoRA from a folder of images. Florence 2 auto-captions, Musubi trains, and a built-in test section previews results.
_1783689800291.png?width=400&height=300&quality=80&resize=cover)
ashree
94
character consistency
character dataset
lora dataset
qwen image edit 2511
Upload a single character image and Qwen Image Edit 2511 generates a full multi-pose training dataset automatically, saving each image with a matching caption file ready for LoRA training.
Qwen 2511 · Single Image to Character Dataset
Upload a single character image and Qwen Image Edit 2511 generates a full multi-pose training dataset automatically, saving each image with a matching caption file ready for LoRA training.
ashree
59
camera control
pan
recammaster
tilt
video to video
WAN2.1
zoom
Upload a video and choose a new camera trajectory. RecamMaster on Wan 2.1 regenerates the video with the new camera path while preserving the scene content, motion, and audio.
Wan 2.1 RecamMaster · V2V Camera Contro
Upload a video and choose a new camera trajectory. RecamMaster on Wan 2.1 regenerates the video with the new camera path while preserving the scene content, motion, and audio.
ashree
65
depth control
flux
restyle
style transfer
video to video
wan2.1 fun control
Upload a video and describe a new visual style. FLUX.1 Dev generates a style reference frame, and Wan 2.1 Fun Control restyles the full video while preserving the original motion, structure, and audio.
Wan 2.1 Fun Control + Flux V2V Restyle
Upload a video and describe a new visual style. FLUX.1 Dev generates a style reference frame, and Wan 2.1 Fun Control restyles the full video while preserving the original motion, structure, and audio.
_1783074667020.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
280
audio sync
audio to video
image to video
ltx2.3
Upload an image and an audio track, describe the scene, and LTX Video 2.3 22B generates a video where the motion, energy, and pacing sync to your audio.
LTX 2.3 Image + Audio to Video · Image to Video
Upload an image and an audio track, describe the scene, and LTX Video 2.3 22B generates a video where the motion, energy, and pacing sync to your audio.
_1783072269036.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
87
image to video
kling avatar v2 pro
lipsync
talking avatar
Upload a portrait and an audio file, and Kling AI Avatar V2 Pro generates a lip-synced talking avatar video with natural expressions, head movement, and 1080p output.
Kling AI Avatar V2 Pro · Photo to Talking Video
Upload a portrait and an audio file, and Kling AI Avatar V2 Pro generates a lip-synced talking avatar video with natural expressions, head movement, and 1080p output.
_1783063183737.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
136
image to video
infinite talk
lipsync
talking avatar
wan2.1
Upload a portrait and an audio file of any length, and InfiniteTalk generates a lip-synced talking avatar video that runs for the full duration of the audio using Wan 2.1 14B with windowed generation.
InfiniteTalk · Image to Video
Upload a portrait and an audio file of any length, and InfiniteTalk generates a lip-synced talking avatar video that runs for the full duration of the audio using Wan 2.1 14B with windowed generation.
ashree
72
fusionx
lipsync
multitalk
wan 2.1
Upload a portrait and an audio file, and Wan 2.1 FusionX with MultiTalk generates a video of the character speaking or singing with precise lip-sync driven by your audio.
Wan 2.1 FusionX MultiTalk · Image to Video
Upload a portrait and an audio file, and Wan 2.1 FusionX with MultiTalk generates a video of the character speaking or singing with precise lip-sync driven by your audio.
_1783001437247.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
96
fashion video
reference to video
seedance 2.0
ugc
virtual try-on
Upload a clothing image and a model photo, and Seedance 2.0 generates a 10-second vertical get-ready-with-me video of the model wearing the outfit with spoken dialogue, natural motion, and native audio.
Seedance 2.0 Virtual Try-On · Reference to Video
Upload a clothing image and a model photo, and Seedance 2.0 generates a 10-second vertical get-ready-with-me video of the model wearing the outfit with spoken dialogue, natural motion, and native audio.
_1783074028007.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
57
dialogue replacement
dubbing
sync lipsync
video to video
Upload a video and a new audio track, and Sync Lipsync 2 Pro replaces the lip movements to match the new audio while preserving facial detail, skin texture, and identity.
Sync Lipsync 2 Pro · Video to Video
Upload a video and a new audio track, and Sync Lipsync 2 Pro replaces the lip movements to match the new audio while preserving facial detail, skin texture, and identity.
_1783176800866.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
62
pose transfer
qwen image edit
restyle
style transfer
video to video
wan2.2
Upload a video, describe the target style, and a parallel pipeline generates a style reference frame with Qwen Image Edit 2511 while Wan 2.2 Animate restyles the full video with pose-guided structural control.
Wan 2.2 + Qwen V2V Restyle · Video to Video
Upload a video, describe the target style, and a parallel pipeline generates a style reference frame with Qwen Image Edit 2511 while Wan 2.2 Animate restyles the full video with pose-guided structural control.
_1783174306365.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
82
image to video
kling 3.0
motion control
motion transfer
Upload a character image and a motion reference video, and Kling 3.0 Pro generates a new video of your character performing the referenced action with the option to keep the original audio.
Kling 3.0 Pro Motion Control · Image to Video
Upload a character image and a motion reference video, and Kling 3.0 Pro generates a new video of your character performing the referenced action with the option to keep the original audio.
ashree
72
vace
video outpainting
video to video
wan2.1
Upload a video and Wan 2.1 with the VACE module extends the frame outward, filling in new content that matches the original scene, motion, and lighting.
Wan 2.1 VACE Outpaint · Video to Video
Upload a video and Wan 2.1 with the VACE module extends the frame outward, filling in new content that matches the original scene, motion, and lighting.
_1782986416296.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
67
accessory
fashion video
seedance 2.0
ugc
Upload a product photo and a model photo, write a timed multi-scene script, and Seedance 2.0 generates a 13-second vertical fashion video with dynamic cuts, varied angles, and native audio.
Seedance 2.0 UGC Fashion Video · Reference to Vide
Upload a product photo and a model photo, write a timed multi-scene script, and Seedance 2.0 generates a 13-second vertical fashion video with dynamic cuts, varied angles, and native audio.
_1772103374491_1782985279298.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
68
ai influencer
product ad
seedream 5.0
wan2.6
Upload a person photo and a product photo, composite them into a styled ad image with Seedream 5.0 Lite, then animate it into a 10-second talking ad with Wan 2.6 at 1080p with native audio and lip-sync.
AI Influencer Ad Generator · Image to Video
Upload a person photo and a product photo, composite them into a styled ad image with Seedream 5.0 Lite, then animate it into a 10-second talking ad with Wan 2.6 at 1080p with native audio and lip-sync.
_1772486002401_1782982124206.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
64
beauty ad
kling
nano banana
product video
Upload a model photo and a beauty product photo, composite them into a styled beauty image with Nano Banana 2, then animate it into a 10-second talking ad with Kling 2.6 Pro and hit run.
AI Beauty Ad Builder · Image to Video
Upload a model photo and a beauty product photo, composite them into a styled beauty image with Nano Banana 2, then animate it into a 10-second talking ad with Kling 2.6 Pro and hit run.
_1771834011124_1782981151767.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
54
ai influencer
nano banana pro
product ad
wan2.6
Upload a person photo and a product photo, composite them into a styled ad image with Nano Banana Pro, then animate it into a 10-second talking ad with Wan 2.6 and hit run.
AI Influencer Ad Generator · Image to Video
Upload a person photo and a product photo, composite them into a styled ad image with Nano Banana Pro, then animate it into a 10-second talking ad with Wan 2.6 and hit run.
_1772389694491_1782979813618.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
78
ai influencer
ltx2
opensource
product video
qwen image edit
Upload a person photo and a product photo, and this two-step workflow composites them into a styled influencer image with Qwen Image Edit 2511, then animates it into a 10-second talking video with synchronized audio using LTX-2 19B.
AI Influencer Video Maker · Image to Video
Upload a person photo and a product photo, and this two-step workflow composites them into a styled influencer image with Qwen Image Edit 2511, then animates it into a 10-second talking video with synchronized audio using LTX-2 19B.
_1772104822143_1782978375956.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
60
ai influencer
kling
nano banana pro
product video
Upload a model photo and a product photo, and this two-step workflow composites them into a styled influencer image with Nano Banana Pro, then animates it into a 10-second talking video with Kling 2.6 Pro.
AI Influencer Video Maker · Image to Video
Upload a model photo and a product photo, and this two-step workflow composites them into a styled influencer image with Nano Banana Pro, then animates it into a 10-second talking video with Kling 2.6 Pro.
_1782976761384.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
67
product video
reference to video
seedance 2.0
tutorial
Upload a product photo and a person photo, write a timed review script, and Seedance 2.0 generates a 15-second vertical product tutorial video with native audio, dialogue, and lip-sync.
Seedance 2.0 Product Tutorial · Reference to Video
Upload a product photo and a person photo, write a timed review script, and Seedance 2.0 generates a 15-second vertical product tutorial video with native audio, dialogue, and lip-sync.
_1782926698029.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
71
cinematic
image to video
kling 3.0
Upload a start image and an optional end image, describe the motion, and Kling 3.0 Pro generates a cinematic video with native audio, lip-sync, and start-to-end frame control at up to 4K resolution.
Kling 3.0 Pro · Image to Video
Upload a start image and an optional end image, describe the motion, and Kling 3.0 Pro generates a cinematic video with native audio, lip-sync, and start-to-end frame control at up to 4K resolution.
_1782914268637.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
87
bytedance
motion transfer
reference to video
seedance 2.0
Upload a character image and a motion reference video. Seedance 2.0 generates a new video of your character performing the action from the reference, with synchronized audio, using the #1-ranked AI video model.
Seedance 2.0 · Reference to Video
Upload a character image and a motion reference video. Seedance 2.0 generates a new video of your character performing the action from the reference, with synchronized audio, using the #1-ranked AI video model.
_1782907563844.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
128
advanced
image to video
ltx2.3
Upload an image and LTX 2.3 22B animates it into a 10-second cinematic video at 1080p with synchronized audio, using a three-pass generation pipeline with spatial upscaling and Negative Attention Guidance for maximum quality.
LTX 2.3 Advanced · Image to Video
Upload an image and LTX 2.3 22B animates it into a 10-second cinematic video at 1080p with synchronized audio, using a three-pass generation pipeline with spatial upscaling and Negative Attention Guidance for maximum quality.
_1782902893383.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
122
ai video
audio
grok imagine
Image to video
xai
Upload a starting image and describe the motion. Grok Imagine Video by xAI animates it into a cinematic clip with synchronized audio, sound effects, and dialogue at 720p.
Grok Imagine Video · Image to Video
Upload a starting image and describe the motion. Grok Imagine Video by xAI animates it into a cinematic clip with synchronized audio, sound effects, and dialogue at 720p.
ashree
141
#1970s
#claude
#live-band
#llm
#music-video
#stage-generation
Drop any performer photo → automatically generate 9 consistent retro disco concert images ready to cut into a music video.
Retro Disco Multi-Scene Concert Generator — GPT 2
Drop any performer photo → automatically generate 9 consistent retro disco concert images ready to cut into a music video.
ashree
585
API
LTX2.3
Animate a still image with LTX-2.3 Pro. Build a prompt from four parts (scene, dialog, ambient, style) and get a clip with lip-synced dialog and audio.
LTX-2.3 Pro - Image to Video with Lipsync
Animate a still image with LTX-2.3 Pro. Build a prompt from four parts (scene, dialog, ambient, style) and get a clip with lip-synced dialog and audio.
Horizontal to Vertical Video Reframe
_1782845684321.png?width=400&height=300&quality=80&resize=cover)
ashree
105
composite
editorial
multi-reference
photoshoot
qwen image edit
Upload three images, a subject, an environment, and a prop or lighting reference, and Qwen Image Edit 2511 composites them into a single photorealistic editorial scene with matched lighting, scale, and perspective.
Qwen Image Edit 2511 · Composite a Photoshoot
Upload three images, a subject, an environment, and a prop or lighting reference, and Qwen Image Edit 2511 composites them into a single photorealistic editorial scene with matched lighting, scale, and perspective.
_1772477545790_1782989405316.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
65
kling
nano banana 2
travel vlog
ugc
Upload a person photo and a location photo, composite them into a selfie-style travel image with Nano Banana 2, then animate it into a 10-second talking vlog clip with Kling 2.6 Pro.
AI Travel Vlogger Generator · Image to Video
Upload a person photo and a location photo, composite them into a selfie-style travel image with Nano Banana 2, then animate it into a 10-second talking vlog clip with Kling 2.6 Pro.
_1782842906311.png?width=400&height=300&quality=80&resize=cover)
ashree
90
extend
flux 2 klein
image expansion
outpaint
Upload an image and FLUX.2 Klein extends the scene outward on both sides, filling in new content that matches the original lighting, perspective, and detail, then upscales the result with SeedVR2.
FLUX.2 Klein Outpaint · Image Expansion
Upload an image and FLUX.2 Klein extends the scene outward on both sides, filling in new content that matches the original lighting, perspective, and detail, then upscales the result with SeedVR2.
_1782836552733.png?width=400&height=300&quality=80&resize=cover)
ashree
96
gpt image 2
image editing
image to image
text rendering
Upload an image and describe the change you want. GPT Image 2 applies the edit while preserving everything you did not ask to change, with reasoning-powered precision and near-perfect text rendering.
GPT Image 2 · Image Editing
Upload an image and describe the change you want. GPT Image 2 applies the edit while preserving everything you did not ask to change, with reasoning-powered precision and near-perfect text rendering.
_1782808991838.png?width=400&height=300&quality=80&resize=cover)
ashree
70
gemini 3 pro
image editing
Image to image
nano banana pro
Write a prompt to generate an image from scratch, or upload an image and describe the change you want. Nano Banana Pro, Google's Gemini 3 Pro image model, handles both in one workflow.
Nano Banana Pro · Generate & Edit Images
Write a prompt to generate an image from scratch, or upload an image and describe the change you want. Nano Banana Pro, Google's Gemini 3 Pro image model, handles both in one workflow.
ashree
157
gemma 4
google deepmind
multimodal llm
video to text
video understanding
Upload a video, ask a question or give an instruction, and get a written answer from Gemma 4 E4B, Google DeepMind's open-weights multimodal model. It reads the frames and the audio track together.
Gemma 4 E4B: Ask Anything About a Video
Upload a video, ask a question or give an instruction, and get a written answer from Gemma 4 E4B, Google DeepMind's open-weights multimodal model. It reads the frames and the audio track together.
_1783607468224.png?width=400&height=300&quality=80&resize=cover)
ashree
61
character consistency
lora dataset
qwen image edit
Upload one reference photo and write a list of scene descriptions. Qwen Image Edit 2509 generates multiple views of the same character across different poses, settings, and angles, saving each image and caption pair ready for LoRA training.
Qwen Image Edit 2509 · Build a LoRA Dataset
Upload one reference photo and write a list of scene descriptions. Qwen Image Edit 2509 generates multiple views of the same character across different poses, settings, and angles, saving each image and caption pair ready for LoRA training.
ashree
235
Api
Image to Image
Outpainting
Reframe any image to a new aspect ratio without cropping. Nano Banana Pro extends the canvas, inventing new background pixels while keeping the original intact.
Image Outpaint to Any Aspect Ratio
Reframe any image to a new aspect ratio without cropping. Nano Banana Pro extends the canvas, inventing new background pixels while keeping the original intact.
ashree
72
high detail
qwen image 2512
text to image
Write a prompt and Qwen Image 2512 generates a high-resolution image at up to 1920x1280 in 50 steps, using Alibaba's latest dedicated image generation model with strong photorealism and bilingual prompt support.
Qwen Image 2512 · Text to Image For Anime
Write a prompt and Qwen Image 2512 generates a high-resolution image at up to 1920x1280 in 50 steps, using Alibaba's latest dedicated image generation model with strong photorealism and bilingual prompt support.
Seedance 2.0 Reference-to-Video with LLM Prompt
HiDream Logo Generator with Qwen EditHidream
_1783682296345.png?width=400&height=300&quality=80&resize=cover)
ashree
76
character consistency
dataset
flux kontext
lora dataset
Upload a single character image and Flux Kontext generates a full multi-pose, multi-angle training dataset automatically, saving each image with a matching caption ready for LoRA training.
Flux Kontext · Single Image to Character LoRA Data
Upload a single character image and Flux Kontext generates a full multi-pose, multi-angle training dataset automatically, saving each image with a matching caption ready for LoRA training.
ashree
85
background removal
film production
LTX2.3
VFX
Video Generation
Video to Video
Remove Anything From Your Video, LTX 2.3 Obscura Just Load a clip, describe what you want gone, and LTX 2.3 erases it across every frame. The rest of the scene stays exactly as you shot it.
LTX 2.3 · Obscura Object Removal from Video
Remove Anything From Your Video, LTX 2.3 Obscura Just Load a clip, describe what you want gone, and LTX 2.3 erases it across every frame. The rest of the scene stays exactly as you shot it.
_1782894825920.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
101
extend video
ltx 2.3
video to video
Upload a video and describe what happens next. LTX 2.3 generates a seamless continuation from the last frame, matching the original motion, lighting, characters, and audio.
LTX 2.3 · Extend Video
Upload a video and describe what happens next. LTX 2.3 generates a seamless continuation from the last frame, matching the original motion, lighting, characters, and audio.
%20(1)_1782890427666.webp?width=400&height=300&quality=80&resize=contain&format=origin)
ashree
71
cinematic
image to video
multi-shot
wan 2.6
Upload a starting image and describe your scene. Wan 2.6 automatically plans and renders multiple camera angles and shot transitions within a single video, with synchronized audio, dialogue, and character consistency.
Wan 2.6 · Multi-Shot Image to Video
Upload a starting image and describe your scene. Wan 2.6 automatically plans and renders multiple camera angles and shot transitions within a single video, with synchronized audio, dialogue, and character consistency.